Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension

Abstract

In multi-turn dialog, utterances do not always take the full form of sentences (Carbonell 1983), which naturally makes understanding the dialog context more difficult. However, it is essential to fully grasp the dialog context to generate a reasonable response. Hence, in this paper, we propose to improve the response generation performance by examining the model's ability to answer a reading comprehension question, where the question is focused on the omitted information in the dialog. Enlightened by the multi-task learning scheme, we propose a joint framework that unifies these two tasks, sharing the same encoder to extract the common and task-invariant features with different decoders to learn task-specific features. To better fusing information from the question and the dialog history in the encoding part, we propose to augment the Transformer architecture with a memory updater, which is designed to selectively store and update the history dialog information so as to support downstream tasks. For the experiment, we employ human annotators to write and examine a large-scale dialog reading comprehension dataset. Extensive experiments are conducted on this dataset, and the results show that the proposed model brings substantial improvements over several strong baselines on both tasks. In this way, we demonstrate that reasoning can indeed help better response generation and vice versa. We release our large-scale dataset for further research.

The Style-Content Duality of Attractiveness: Learning to Write Eye-Catching Headlines via Disentanglement

“…Headline Generation. In recent years, text generation has made impressive progress (Li et al 2019;Chan et al 2019;Liu et al 2020;Xie et al 2020;Chan et al 2020;Chen et al 2021), and headline generation has become a research hotspot in Natural Language Processing. Most existing headline generation works solely focus on summarizing the document.…”

Learning towards Selective Data Augmentation for Dialogue Generation

“…Open-domain dialogue generation is becoming a research hotspot in the community of natural language processing due to its penitential applications (Li et al 2019;Chen et al 2021b). Generally, in the paradigm of deep neural networks, a large quantity of training data is required for facilitating the convergence of these models.…”